Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to surnames or place names, specifically those containing "field"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to people’s last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILA
    -0.89
    externalActionCode
    -0.82
    bian
    -0.81
    Magikarp
    -0.79
    nces
    -0.75
    ittance
    -0.74
    ailability
    -0.74
    thood
    -0.73
    éĹĺ
    -0.71
    é¾įåĸļ士
    -0.70
    POSITIVE LOGITS
    field
    0.86
    er
    0.78
    fields
    0.76
    shire
    0.76
    ers
    0.74
     Junction
    0.69
     Marshal
    0.69
     Landing
    0.68
     Farms
    0.67
    hurst
    0.66
    Act Density 0.012%

    No Known Activations